© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35627
    Prev
    Next
    INDEX
    Explanations

    ut

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     విశ
    0.40
    シル
    0.40
    갸
    0.39
     Gaul
    0.39
    𝐮
    0.38
     utt
    0.37
     رو
    0.37
    צר
    0.37
    ரு
    0.37
    किल
    0.37
    POSITIVE LOGITS
     Prote
    0.42
    닝
    0.42
    บาด
    0.42
    prote
    0.40
    ierno
    0.39
    ाइड
    0.39
    >{</
    0.38
    tenham
    0.38
    nica
    0.37
    usan
    0.37
    Activations Density 0.001%

    No Known Activations